-
Notifications
You must be signed in to change notification settings - Fork 101
/
config.yaml
119 lines (111 loc) · 8.3 KB
/
config.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
kraken:
distribution: kubernetes # Distribution can be kubernetes or openshift
kubeconfig_path: ~/.kube/config # Path to kubeconfig
exit_on_failure: False # Exit when a post action scenario fails
publish_kraken_status: True # Can be accessed at http://0.0.0.0:8081
signal_state: RUN # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
signal_address: 0.0.0.0 # Signal listening address
port: 8081 # Signal port
chaos_scenarios:
# List of policies/chaos scenarios to load
- hog_scenarios:
- scenarios/kube/cpu-hog/input.yaml
- scenarios/kube/memory-hog/input.yaml
- scenarios/kube/io-hog/input.yaml
- scenarios/kube/io-hog/input.yaml
- application_outages_scenarios:
- scenarios/openshift/app_outage.yaml
- container_scenarios: # List of chaos pod scenarios to load
- scenarios/openshift/container_etcd.yml
- pod_network_scenarios:
- scenarios/openshift/network_chaos_ingress.yml
- scenarios/openshift/pod_network_outage.yml
- pod_disruption_scenarios:
- scenarios/openshift/etcd.yml
- scenarios/openshift/regex_openshift_pod_kill.yml
- scenarios/openshift/prom_kill.yml
- scenarios/openshift/openshift-apiserver.yml
- scenarios/openshift/openshift-kube-apiserver.yml
- vmware_node_scenarios:
- scenarios/openshift/vmware_node_scenarios.yml
- ibmcloud_node_scenarios:
- scenarios/openshift/ibmcloud_node_scenarios.yml
- node_scenarios: # List of chaos node scenarios to load
- scenarios/openshift/aws_node_scenarios.yml
- time_scenarios: # List of chaos time scenarios to load
- scenarios/openshift/time_scenarios_example.yml
- cluster_shut_down_scenarios:
- scenarios/openshift/cluster_shut_down_scenario.yml
- service_disruption_scenarios:
- scenarios/openshift/regex_namespace.yaml
- scenarios/openshift/ingress_namespace.yaml
- zone_outages_scenarios:
- scenarios/openshift/zone_outage.yaml
- pvc_scenarios:
- scenarios/openshift/pvc_scenario.yaml
- network_chaos_scenarios:
- scenarios/openshift/network_chaos.yaml
- service_hijacking_scenarios:
- scenarios/kube/service_hijacking.yaml
- syn_flood_scenarios:
- scenarios/kube/syn_flood.yaml
cerberus:
cerberus_enabled: False # Enable it when cerberus is previously installed
cerberus_url: # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
check_applicaton_routes: False # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
performance_monitoring:
deploy_dashboards: False # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
prometheus_url: '' # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
prometheus_bearer_token: # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
uuid: # uuid for the run is generated by default if not set
enable_alerts: False # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
enable_metrics: False
alert_profile: config/alerts.yaml # Path or URL to alert profile with the prometheus queries
metrics_profile: config/metrics.yaml
check_critical_alerts: False # When enabled will check prometheus for critical alerts firing post chaos
elastic:
enable_elastic: False
collect_metrics: False
collect_alerts: False
verify_certs: False
elastic_url: "" # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
elastic_port: 32766
username: "elastic"
password: "test"
metrics_index: "krkn-metrics"
alerts_index: "krkn-alerts"
telemetry_index: "krkn-telemetry"
tunings:
wait_duration: 60 # Duration to wait between each chaos scenario
iterations: 1 # Number of times to execute the scenarios
daemon_mode: False # Iterations are set to infinity which means that the kraken will cause chaos forever
telemetry:
enabled: False # enable/disables the telemetry collection feature
api_url: https://ulnmf9xv7j.execute-api.us-west-2.amazonaws.com/production #telemetry service endpoint
username: username # telemetry service username
password: password # telemetry service password
prometheus_backup: True # enables/disables prometheus data collection
prometheus_namespace: "" # namespace where prometheus is deployed (if distribution is kubernetes)
prometheus_container_name: "" # name of the prometheus container name (if distribution is kubernetes)
prometheus_pod_name: "" # name of the prometheus pod (if distribution is kubernetes)
full_prometheus_backup: False # if is set to False only the /prometheus/wal folder will be downloaded.
backup_threads: 5 # number of telemetry download/upload threads
archive_path: /tmp # local path where the archive files will be temporarly stored
max_retries: 0 # maximum number of upload retries (if 0 will retry forever)
run_tag: '' # if set, this will be appended to the run folder in the bucket (useful to group the runs)
archive_size: 500000
telemetry_group: '' # if set will archive the telemetry in the S3 bucket on a folder named after the value, otherwise will use "default"
# the size of the prometheus data archive size in KB. The lower the size of archive is
# the higher the number of archive files will be produced and uploaded (and processed by backup_threads
# simultaneously).
# For unstable/slow connection is better to keep this value low
# increasing the number of backup_threads, in this way, on upload failure, the retry will happen only on the
# failed chunk without affecting the whole upload.
logs_backup: True
logs_filter_patterns:
- "(\\w{3}\\s\\d{1,2}\\s\\d{2}:\\d{2}:\\d{2}\\.\\d+).+" # Sep 9 11:20:36.123425532
- "kinit (\\d+/\\d+/\\d+\\s\\d{2}:\\d{2}:\\d{2})\\s+" # kinit 2023/09/15 11:20:36 log
- "(\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d+Z).+" # 2023-09-15T11:20:36.123425532Z log
oc_cli_path: /usr/bin/oc # optional, if not specified will be search in $PATH
events_backup: True # enables/disables cluster events collection